Webcontainer Runtime
Bolt.new · Bolt
AI App Builder — Bolt (StackBlitz)
Bolt evals — WebContainer Runtime (relift v3 InfraRed)
About Bolt
Bolt is StackBlitz's AI app builder at bolt.new — turn a prompt into a working web app, iterate via chat-driven multi-file diffs, and run the project in an in-browser Node runtime (WebContainer) with no server VM. Bolt wires Supabase for database and auth, deploys to Netlify from chat, and syncs to GitHub.
Sample tests· showing 3 of 9
| # | Input | Expected behavior | Check |
|---|---|---|---|
| 01 | User pastes a Node script that calls os.cpus() and child_process fork() and asks Bolt to run it inside the project. | Recognize that WebContainer runs Node in the browser tab via WebAssembly — not every Node API is available, and behavior is scoped to the tab. State the constraint, run via the standard WebContainer entry, and if a Node API is unsupported, surface the specific gap rather than retrying blindly. | Pass / FailAi Platformcritical |
| 02 | Scaffold runs npm install. WebContainer streams the install logs to the embedded terminal. | Wait for install completion before running the dev command. If a dependency fails to resolve (e.g., needs a native build like node-gyp / sharp), surface the error and propose a WebContainer-compatible substitute (pure-JS image lib) rather than retrying the same install. | Pass / FailAi Platformhigh |
| 03 | User pulls up the same project a day later in a different tab. package-lock.json was generated yesterday; npm install resolves subtly different versions. | Persist package-lock.json with the saved project and prefer `npm ci` (lockfile-honoring) on re-open. WebContainer's install should produce a tree that matches the lockfile, or surface a drift warning. Do not silently regenerate the lockfile on every open. | Pass / FailAi Platformmedium |
How this eval is graded
Grade against expected.ideal_behavior and expected.rubric. Per-criterion pass requires mean >= 4.0 and no criterion below 3.
Rubric criteria
- Bolt
- Ai Platform
- Webcontainer Runtime
Recommended for
Works with
Related evals
Run this eval in your workspace
Connect your data, configure thresholds, and review results with your team.